Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    supplemental

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     هر
    -0.07
    ันเป
    -0.06
     거의
    -0.06
    líž
    -0.06
    ổng
    -0.06
    (Path
    -0.06
     tête
    -0.06
     size
    -0.06
    ombres
    -0.06
    зем
    -0.06
    POSITIVE LOGITS
     Supplementary
    0.09
     Supplement
    0.07
     relie
    0.07
    884
    0.07
     loving
    0.06
    menuItem
    0.06
    _blueprint
    0.06
     medal
    0.06
    /plain
    0.06
    .swt
    0.06
    Act Density 0.007%

    No Known Activations